jriou/yt-mp3-ui
1
0
Fork 0
Code Activity

[utils] is_html: Handle double BOM

Browse source 
Closes #2885
This commit is contained in:
pukkandan 2022-05-18 06:42:43 +05:30
commit 80e8493ee7
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
2 changed files with 20 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

13
yt_dlp/utils.py
View file

@ -3290,14 +3290,13 @@ def is_html(first_bytes):
(b'\xff\xfe', 'utf-16-le'),
(b'\xfe\xff', 'utf-16-be'),
]
for bom, enc in BOMS:
if first_bytes.startswith(bom):
s = first_bytes[len(bom):].decode(enc, 'replace')
break
else:
s = first_bytes.decode('utf-8', 'replace')
return re.match(r'^\s*<', s)
encoding = 'utf-8'
for bom, enc in BOMS:
while first_bytes.startswith(bom):
encoding, first_bytes = enc, first_bytes[len(bom):]
return re.match(r'^\s*<', first_bytes.decode(encoding, 'replace'))
def determine_protocol(info_dict):